Acquisition
Iris capture requires optical and distance conditions appropriate to the device. Public documentation does not attribute NIR, single-eye or binocular capability to CheckID without a tested profile.
BIOMETRIC SCIENCE
Iris — capture, segmentation, template and matching
Iris requires suitable capture, quality control and segmentation before representation. separates enrollment, verification and identification and links the modality to compatible devices.
SOURCEAuthoritative / document
CAPTUREDevice / SDK
VERIFYDocument + biometric
ASSUREPolicy + risk
DECIDEClaims / status
EVIDENCEAudit / trace
Technical basisSOURCE-BACKED
SourceCheckID CheckID + ISO standards register
StandardISO/IEC 39794-6
VersionCurrent published edition per standard
ApplicabilityModality-specific; implementation dependent
EvidenceProcess types + standards mapping + certificate scope
TECHNICAL REFERENCE
Iris: acquisition, segmentation and operating profile
Eye acquisition → localization/segmentation → quality → template → 1:1/1:N
Segmentation
Eye/iris localization and segmentation must address eyelid/eyelash/occlusion/reflection according to the engine. Algorithm details absent from sources are not inferred.
Quality
Focus, usable iris region, occlusion and capture consistency are modality-specific quality dimensions rather than a generic cross-biometric score.
Enrollment
Enrollment should define eye/sample association, template/version and re-capture handling according to actual product sources.
1:1 / 1:N
Verification and identification use different protocols and performance measures. The API catalog supports `IRIS_IDENTIFICATION` in the identification-group context but provides no operating benchmark.
Failure and evidence
No eye, poor focus, excessive occlusion, segmentation failure, missing reference and search no-match are distinct classes to map to implementation results when source evidence exists.
Authoritative technical references
- ISO/IEC 19795-1:2021 — Biometric performance testingPublished; revision under development